Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    personal information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     quirk
    0.46
    ueva
    0.41
     permanece
    0.39
     guardianship
    0.39
     expressed
    0.38
     ඇති
    0.38
     perpetuated
    0.38
    amam
    0.38
     parishes
    0.37
    ন্ধ
    0.37
    POSITIVE LOGITS
    Autom
    0.47
    Alg
    0.45
     Sound
    0.44
    Collection
    0.43
    Autonomous
    0.43
    Sound
    0.42
    Implement
    0.41
    ה
    0.41
     Roadmap
    0.41
    денти
    0.41
    Act Density 0.000%

    No Known Activations